云平台的任务优先级调度研究

发布时间：2018-04-11 04:14

本文选题：云平台 + 任务调度　；参考：《河北工程大学》2015年硕士论文

【摘要】：云平台虚拟化技术不但使得软件应用具有更高的效率,也给任务调度与资源管理带来了新的机遇。随着云平台的任务逐渐增加,一些调度任务之间的关联性逐渐淡化,传统云平台任务调度模型,无法运用准确的约束关系确定其先后顺序,造成资源利用效率低、空闲时间高和任务请求缺失率高等弊端。本文提出一种云平台的任务优先级调度模型,对云平台任务调度进行了描述,探讨了平均响应时间与平台调度任务量之间的关联,对任务优先级进行计算,在任务队列中对任务优先级作适当的处理。对任务分配阶段响应平均时间等特性作适当的分析,优先对优先等级高的分配任务进行调度。将任务分配优先级运用起来,使得平均响应时间最小化的同时,达到任务执行量的最大化。仿真实验结果表明,所提模型降低了云平台的平均响应时间,使得资源具有更高的使用效率。
[Abstract]:Cloud platform virtualization technology not only makes software applications more efficient, but also brings new opportunities for task scheduling and resource management.With the increasing of the tasks in cloud platform, the correlation between some scheduling tasks is gradually desalinated. The traditional cloud platform task scheduling model can not use accurate constraints to determine its order, resulting in low efficiency of resource utilization.The disadvantages of high idle time and high missing rate of task request.This paper presents a task priority scheduling model for cloud platform, describes the task scheduling of cloud platform, discusses the relationship between the average response time and the task quantity of the platform scheduling, and calculates the priority of the task.The task priority is properly handled in the task queue.The characteristics of average response time in the task allocation phase are analyzed properly, and priority is given to the scheduling of tasks with high priority level.The task allocation priority is applied to minimize the average response time and maximize the task execution.The simulation results show that the proposed model reduces the average response time of the cloud platform and makes the resources more efficient.
【学位授予单位】：河北工程大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：TP393.09

【参考文献】